Word Embeddings for Wine Recommender Systems Using Vocabularies of Experts and Consumers

Christophe Cruz (1) , Cyril Nguyen Van , Laurent Gautier (2)

1 Le2i - Laboratoire Electronique, Informatique et Image [UMR6306]
2 MSH Dijon (MSHD) - Maison des Sciences de l'Homme de Dijon

This vision paper proposes an approach to use the most advanced word embeddings techniques to bridge the gap between the discourses of experts and non-experts and more specifically the terminologies used by the two communities. Word embeddings makes it possible to find equivalent terms between experts and non-experts, by approach the similarity between words or by revealing hidden semantic relations. Thus, these controlled vocabularies with these new semantic enrichments are exploited in a hybrid recommendation system incorporating content-based ontology and keyword-based ontology to obtain relevant wines recommendations regardless of the level of expertise of the end user. The major aim is to find a non-expert vocabulary from semantic rules to enrich the knowledge of the ontology and improve the indexing of the items (i.e. wine) and the recommendation process.

Mots clés: Wine; Recommander systems; Ontology; Word embedding; Semantics; Terminology; Expert Discourse

Domaines: Linguistique

Christophe Cruz, Cyril Nguyen Van, Laurent Gautier. Word Embeddings for Wine Recommender Systems Using Vocabularies of Experts and Consumers. Open Journal of Web Technologies, 2018, Special Issue: Proceedings of the International Workshop on Web Data Processing & Reasoning (WDPAR 2018) in conjunction with the 41st German Conference on Artificial Intelligence, 5 (1), pp.23-30. ⟨halshs-01872273⟩